Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3979 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8432. Min Range: -5.8432
Max Act: 5.8432. Min Act: -0.1700
Data Index: 2840552 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8432. Min Range: -5.8432
Max Act: 5.7807. Min Act: -0.1700
Data Index: 7424264 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8432. Min Range: -5.8432
Max Act: 5.7807. Min Act: -0.1700
Data Index: 3384890 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8432. Min Range: -5.8432
Max Act: 5.7807. Min Act: -0.1700
Data Index: 4923175 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8432. Min Range: -5.8432
Max Act: 5.7182. Min Act: -0.1700
Data Index: 8623858 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8432. Min Range: -5.8432
Max Act: 5.7182. Min Act: -0.1700
Data Index: 6204216 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8432. Min Range: -5.8432
Max Act: 5.6870. Min Act: -0.1700
Data Index: 6204211 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8432. Min Range: -5.8432
Max Act: 5.6870. Min Act: -0.1700
Data Index: 531688 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8432. Min Range: -5.8432
Max Act: 5.6870. Min Act: -0.1700
Data Index: 724069 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8432. Min Range: -5.8432
Max Act: 5.6557. Min Act: -0.1700
Data Index: 2566860 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8432. Min Range: -5.8432
Max Act: 5.6557. Min Act: -0.1700
Data Index: 7889652 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8432. Min Range: -5.8432
Max Act: 5.6245. Min Act: -0.1700
Data Index: 3779322 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8432. Min Range: -5.8432
Max Act: 5.6245. Min Act: -0.1700
Data Index: 319341 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8432. Min Range: -5.8432
Max Act: 5.5932. Min Act: -0.1700
Data Index: 699172 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8432. Min Range: -5.8432
Max Act: 5.6245. Min Act: -0.1700
Data Index: 3735305 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8432. Min Range: -5.8432
Max Act: 5.5932. Min Act: -0.1700
Data Index: 8102872 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8432. Min Range: -5.8432
Max Act: 5.5932. Min Act: -0.1700
Data Index: 2566851 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8432. Min Range: -5.8432
Max Act: 5.5932. Min Act: -0.1700
Data Index: 255848 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8432. Min Range: -5.8432
Max Act: 5.5932. Min Act: -0.1700
Data Index: 6604795 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8432. Min Range: -5.8432
Max Act: 5.5932. Min Act: -0.1700
Data Index: 3124253 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19